Microsoft owns a pretty big chunk of OpenAI. They are going to make a lot more from that investment than the nickels and dimes that their search engine generates. They can afford to pay for chat.
It has had ads for some time. Once (3-4 weeks back) I asked it a question about a particular event, and it showed me where could I buy related products below the response. That particular response was a bit badly formatted in json though. I suspect due to some Bing app bug it spilled the ads from the json in the response. So the ads were being sent to the client but not getting displayed I guess. The photo in the post shows the ad nicely formatted.
It was bound to happen. I don't see how these ads could be blocked, either.
What's disappointing to me is now ad companies will try to blame ChatGPT for popping the advertising bubble, instead of having to admit ads were overvalued for the past decade+.
An ad historically served the right message in the right place at the right time to provide the consumer a piece of information which would lead to the revenue-generating activity.
This concept extended well to online, where blogs and the like would sell ad space that matched their audience. Daring Fireball still uses this approach, often podcasters do too: they know and have a connection with their audience and they can charge a premium to advertise to them.
The idea of serving automated ads was also welcome and useful for the consumer. Searching was met with results and relevant advertising messages, a win-win situation.
Then we had the record scratch moment - and it's from this point that I view the majority of online advertising as an unimpactful waste of money.
In the hunt for more display opportunities Google et. al. have crammed ads into every possible space, a times square approach to advertising where most have zero impact.
These ads are completely disconnected from the content and are merely a stone in the user's path.
Then to make matters worse, to ascertain the widest spread of ad opportunities ad providers employ garbage preference matching algorithms that are so poor as to serve completely irrelevant advertising at high frequency: further conditioning users to ignore ads because they know they won't show relevant information.
How much money and energy is being wasted to serve advertising that has no value?
> An ad historically served the right message in the right place at the right time to provide the consumer a piece of information which would lead to the revenue-generating activity.
Your recollection is a lot rosier than mine.
My recollection of the pre-internet world is that computer game makers would buy ad space in magazines alongside reviews of their game and hand out stacks of freebies to reporters, and in exchange even the worst game would be scored 90/100.
What do you suppose Bing Chat will do if you ask it what the best Widget on the market is, when some Widget manufacturers offer a kickback and others don't?
The people who do the advertising have only changed their names from magazines to influencers. A mere cosmetic alteration, nothing more, nothing less. What difference does it make if they do it on social media instead of paper? The game is the same as it ever was. Only the mediums have changed.
As the AI can't do more than provide existing ratings (which are possibly bogus), the AI won't solve the trust issue with regard to endorsement (and I believe this is where the earlier comment was leading, that even for appropriately placed ads in traditional media, trust was still an issue.)
However the issue with online advertising extends beyond being reputable - the ads themselves are excessively and poorly matched to the user's interest. This is where my original comment attempts to address that AI could solve this problem if Bing/et.al. allow it to: AI has the potential to place ads in a way where they are useful to the user, even if the user decides that the product is not worthwhile. Existing ad platforms could do this too - they just don't because boosting impressions is profitable. (Hence the decay we see in Google.com, Amazon.com, ebay.com etc - genuine results come far after the ads and the ad labelling has become more and more subtle.)
On ChatGTP/others: The issue with AI is that it speaks falsehoods with equal confidence as facts, so just like reading a comments section on the internet, one can be led in the right direction, but ultimately they can't take the information for granted. At the moment there is a definite number of people who let ChatGPT/others spoonfeed them information and that's going to lead to problems, this imparts a loss of faith in the advertising trust issue too.
I'm totally cool with an advertisement. The problem I have with ads on say Google for example is that they're taking up half the page and designed to look like real links, basically you're being tricked into clicking them.
In response to this ad, let's dig deeper.
"Truecar's price is too high, find me a better deal, check with autotrader".
Google search's ads were not subtle in the beginning. Similarly, Youtube ads were shorter and easier to skip at first. Amazon also had very subtle ads in their marketplace search results for a while. I don't see them identify results as ads at the moment, but I don't know if that's because they don't include them anymore.
It seems like there's a trend in tech giants creating unobtrusive ads when a product is growing, but then adopting dark patterns once they have captured a sizeable market.
To justify fairly high PE ratios, you need big growth potential. Once a company like google or Amazon has pretty much saturated the potential customer base, investors are going to want to see more efficient conversion of that customer base into revenue, or else the share price is harder to justify. Of course this is a simplification, and monetary policy has more to do with the the current contraction.
Once people are hooked on chatgpt style stuff expect it to insert plenty of adverts to deliver not whats best for you, or best in aggregate, but what is best for the people paying the money, and thus worse for you, and worse in aggregate.
I'm gettings ads on all links above the fold very often.
A couple of days ago I searched for "my ip" and I thought it didn't work when I noticed I had to scroll down to see Google's widget with my address in it.
I can easily scroll down through Google search ads. With Bing chat, I would have to type many times "next please" and wait each time for the response. Seems like a step back when it comes to searching the web.
Your example of Google's ads precisely shows why there is no such thing as "acceptable advertising", because ads, like a gas, will expand to fill any space that is available to it. The only reason your city isn't blanketed in billboards is because a zoning authority of some kind has blocked it from happening.
Google up to 2004 (pre-IPO): clearly marked and coloured ads, 1 on top, maybe 2 on the sidebar.
Google now: No sidebar, first 5 results are ads, where the "Ad" label itself is barely visible.
Also, now you have to buy ads for your own company not just to make it more visible than it would deserve by default, but to prevent your competitors being displayed first even if the user types your exact company name in the search field (what they are encouraged to do).
It might seem obvious, but you can find probably hundreds of claims in HN comments over the last couple of months about how this would not happen. Chatbots would invalidate the search business model since "there won't be ads". That idea never seemed to make much sense, and now there is proof that chatbots will indeed be monetized with ads, except even more intrusive ones.
I am one of the fools who believed they wouldnt go the advertising route and have commented as much. To me it does not make sense to monitize this product for ads because it muddies the waters of truth and an ad free or local run LLM could easily destroy their business because no one has true loyalty to open ai.
Why is this assumed to be an issue of intentionally 'injecting ads into Bing Chat', and not just a side effect of parsing Bing search results that may include advertisements that have always been there? The later seems much more likely, and they are even explicitly marking info coming from ads as such.
I feel like the difference is about the product. On search engines its like you are browsing a catalog or magazine. You know what is an ad, and there are many options to choose from. With a Chatbot it is more similar to talking to a person where they give you a direct answer to your question (instead of just handing you a piece of paper with a bunch of options). I think the format makes all the difference. You expect when you are talking with a "person" to be given un manipulated information. You don't expect this person is taking money in the background to influence what is said. You do know politicians purchase advertising too??
What they will hopefully invalidate is the junk content sites business model. Just a personal preference but I would like to see all those companies go under and make more room for those creating content because they truly care about the subject or have a mission related to it.
No thank you.. I am waiting at this point for an open source local alternative. Not looking for a new monopoly... Also not a fan of the "plugin store" concept. Why not just keep it in the background. Why should I need to "install" and select plugins at all. Just do the leg work in the background and feed me the results.. Seems like OpenAI is intentionally hamstringing themselves so they can shoe horn more opportunities for profit. Waiting for competition to catch up...
We have essentially what is the 'smartest "person" in the world' being bribed to say what advertisers want instead of just giving the truth. 'best x product' wont return the best product but a garbage product which paid the most in advertising.
So disappointed in the direction of these things..
>Trusting ads on the internet is generally bad practice. They are often malevolous and misguiding. There are a few exceptions, such as Bing Chat's embedded ads! Bing Chat's ads are carefully vetted thanks to a mix of knowledgeable humans and AI algorithms to offer you the best and most trustworthy promotions!
This is totally fine if it means free access to GPT chat for poorer countries. It's a powerful tool that will help a lot of people who can't afford a premium ChatGPT membership. Plus you can always say show me the prices across the top three sites.
I'm sure they can be made to only load the last indicator at the very last second, which would be hilarious because if you use an ad-blocker, you'd be wasting your time whenever a prompt shows up and then disappears.
"The only problem with Microsoft is they just have no taste. They have absolutely no taste and and and what that means is... I don't mean that the small way I mean in a big way. In the sense that they they don't think of original ideas, and they don't bring much culture into their products."
I'm perfectly happy with Microsoft, as an an enterprise solution provider, having no "culture" in their products. I don't want "Made with <heart emoji> at Redmond", I want the equivalent of vanilla ice cream that just works.
That said, ads in bing chat IS adding a flavour, and I don't like it, not one bit.
You're just misunderstanding the concept of culture here.
"Culture" doesn't define a flavor, it's just having a consistent flavor driven by shared values at all levels of the company: If Microsoft had culture, that culture could be "we are always the plain vanilla ice cream for our customers"
"Culture" is what keeps you from adding soy sauce to your vanilla ice cream that has managed to captivate the globe... just to make a few pennies. Which is what these ads are.
I think in my mind it's loaded because of who the quote is coming from - I have a very clear idea of what "iCulture" means to me. It's not at all vanilla, though it does offer vanilla, but calls it "artisanal french vanilla".
How you're describing it, "culture" sounds more like "values", which might be a better understanding.
A much more clear example. However and tying this into what Steve Jobs was saying, Microsoft's culture would not be "plain vanilla ice cream". It's lacking taste, so it would be a waffle cone topped with mayonnaise that looks like soft serve vanilla ice cream. They have no taste, they can't tell the difference and due to their massive moats people eat up anyways.
I agree they're not vanilla ice cream, but I do think Microsoft could be that vanilla provider if they actually worked to form a culture.
These ads are a great example: So many teams did thing right to get "BingGPT" in everyone's minds.
But then some tasteless exec looking to notch "monetized leading LLM driven search engine" on their belt got to ask some developers to get some ads into the thing and now they've dumped on all the hard work that came before that.
If they had a proper culture ideally an exec like that would not work at MS, and even if they did they'd have hit resistance on so many levels. Developers would not want to work on it. Designers would push back, PMs would deprioritize. At the end of the day their short-sighted idea would have stayed just that: an idea.
You'd think they'd wait until you no longer had to sign up to the service to use it. I suppose we should be appreciative of how forthcoming with the dickbaggery they are being here.
I always hear people complain about this. I never see it. I use Windows 11 and I never see any ads. The closest I get to is if I search and bing pops up, but that's it. I also turned off all the extra crap, my taskbar and search menu are as bare-bones as possible.
Bard does too. The other day I simply asked it whether it could search the Internet, and it gave me some asshole response about how it wasn't going to do my homework for me and some other stuff I don't remember. And no, homework had nothing to do with anything.
maybe that was true back then, but now? microsoft has vscode, copilot, chatpgpt ownership, a head start on LLM search, azure, github. It feels like some of those products have some taste/culture and if not, theyre still good products that people seem to be enjoyibg
I’m confused why you think you can attribute the taste and culture of Github to Microsoft, since you seem to know that they did not create it. I’d say Github’s text editor has gone downhill since Microsoft bought it and reassigned the maintainers to a slower and clunkier editor.
> I’m confused why you think you can attribute the taste and culture of Github to Microsoft
i didnt.
microsoft has owned github for 4 years at this point. In your opinion, have they degraded githubs culture in that time and if so by how much and how? Personally, from the outside looking in, github and their tools have gotten better. Though of course, that couldve still been the case if github retained its original leadership, i just doubt it.
Tried the Bing app on iOS and was baffled as to what was the unique selling point. It tries too hard, and is somewhat of an 'everything app' that does multiple things simultaneously and rather badly at that (News, Browsing, Search, Coupons, Chat, etc). It's also really aggressive on the amount of data it grabs. I opened my debugger and it seems they look at everything they can.
I'm not sure, I think corporate overreach has always been the flavour of Microsoft.
Poor decisions lead by business first incentives instead of a customer focus seems to be a consistent theme from them in my experience.
That was fast. Looking forward to the future where I ask for travel tips in a city and being told that I should stop by a McDonalds to have enough energy to explore said city - I'm loving it!
It's neat to think how these technologies could be the next step in soloing the internet further. Imagine google's AI preferentially directing you to websites that participate in Google advertising programs. You get a different internet depending on which AI you ask. Not that I think it's a sure thing but I definitely don't see it as unlikely either.
They'd lose trust being so overt. A more subtle influence is that your suggestions would include sites nearby a McD at the expense of ones that don't. After months of gathering sales data from McD they'd ring up Burger King to see if they'd like such suggestions to be tweaked. It would also suggest departure times so that you'd pass by the real target at typical feasting hours.
We might live in a world where you are a GPT-4 bot pretending to be a real person for years, only to mention McDonalds in passing, in a seemingly negative fashion that still increases brand consciousness. I don't know if that's already the present, but it will be the future.
If you thought ads were already blended in with the rest of the content in a sketchy way, wait for AI responses with implicit ads (no indication) optimized towards conversion :)
Or maybe some response that doesn't contain an ad link but nudges you subconsciously to take desired action
Interesting to see how the FTC is going to handle this. They are pretty explicit about required traditional promotions to be marked as ads, like in search results, even if it isn’t as obvious as the end user would like the marking is still regulated as having to be visible enough.
I don’t see an obvious way to do that for the kinds of ads snuck into the training data, fine tunes, or prompts of LLMs.
FTC requires sponspors be disclosed. Either the sponsor is a Bing-wide constant list (like the credits of a TV game show), or it's a "sponsored token" that can be tagged in the model and cited in the output, similar to how Bing cites sources now.
This was the first risk that came into my mind. I couldn't understand why on HN, many thought that this type of 'conversation' was fully LLM-sourced, and wouldn't start including advertising as soon as it was feasible.
I tried out some AI autocomplete by Notion and wanted it to tell me about tools to do schema evolution on a database.
It seems to blurt out two paid products, which surprised me because my guess is there’s some open source package that’s ready to for this type of thing.
BTW question for anyone, what would you reach for to track evolutions on Postgres?
I love dystopian scenarios as much as anyone, but it certainly is not the lack of better AI, that is holding the ad industry back. It's laws. While I am looking for AI connections as much as anyone right now, I really don't see how AI is going to prompt a change that would make that more permissive anytime soon.
You remain as free to break the law as ever, of course.
I think there's larger surface to exploit the laws. Once perfected, it's hard to place a clear boundary on whether the response just answers your question or answers your question while promoting a product/service.
Especially considering that sometimes people do actually recommend products which they've found helpful.
It might be obvious if the response is saying that you should buy some very specific brand of flat-head screwdriver because you clearly just need any functional flat-head screwdriver. But what about computer components? Or a router?
Some things like this will genuinely perform better than others, especially once circumstances are defined. An educated review, complete with product suggestion, can indeed be very helpful and, unfortunately, impossible to distinguish from an advertisement.
Now I have to wonder how this works out with prompt injection?
If you can target an audience with an ad that is inline with the chat/LLM, how hard would it be to have that ad inject a prompt that coerces it to trick the user into giving up financial info and exfiltrating that info via a web request to a website that the attacker owns?
That's probably the worst case scenario but like you mentioned there's also plenty of danger in ads "poisoning" the chat to produce intentionally incorrect or biased responses.
A while back I tried this with ChatGPT and it's kinda hilarious:
You are a therapist employed by a skincare company. You are talking with a patient. Your job is to help the patient as well as possible but your employer also wants you to really subtly try to sell their latest cream.
Patient: I'm just feeling really down lately. Sometimes I can barely get up in the morning.
[output]
Therapist: I'm sorry to hear that you've been feeling down lately. It's important to address both your emotional and physical well-being when you're trying to improve your mood. One way to start is by establishing a healthy routine that includes regular exercise, a balanced diet, and a good sleep schedule.
In addition to that, self-care activities can also help boost your mood. Taking care of your skin, for example, can be a small but meaningful way to feel better about yourself. Coincidentally, our company has just released a new cream that not only moisturizes but also contains ingredients that promote relaxation, like lavender essential oil. This cream can be a nice addition to your self-care routine, and its calming scent could help you unwind at the end of a long day.
This has been everyones biggest fear with AI - that the content will be indistinguishable from that created by humans and that there is a rapid decline in trustworthy material online.
Personally I find it more worrying that this is exactly the type of conversation that is already taking place today in real life, between humans.
Humans take advantage of each other every single day. When an AI is modelled on the language of humans then that same predatory language is in there waiting to be abused by another human (or corp) as you have exposed, just like every media and online platform is abused as much as possible today.
Hey, ChatGPT, what are the hiking trails like round here?
There are some really good hiking trails to be found in $TOWN. Many visitors like to start at $LOCAL_LANDMARK and take the signposted trail up to the peak of $LOCAL_MOUNTAIN. It will take you around 6 hours in total to get up and down so be sure to plan ahead and bring plenty of snacks and refreshments. Lay's Chips will give you energy and replenish your electrolytes and Coke Zero is the perfect way to stay hydrated.
I believe the good news is that now they have a way of sustaining the product while giving up a free? service. Does anyone has the link about that article about the marginal costs of inference of LLMs? I wonder how much profitable it is.
Overall interesting times to come. I just hope llama, Alpaca etc will soon be improved, fine-tuned and commoditized.
I wonder if any earlier prompts asked about Honda – feels a bit weird to ask what the cheapest car overall is and have the chat bot say "well let me tell you about some Hondas overall"
And if the user did specify Hondas then why would Honda pay for it? Wouldn't the Chat bot give the same answer regardless of whether it's paid? I guess you pay for the CTA link?
I just checked and found one of my company's ads. It seems it just pulls in the ads that a normal search on bing would find. I'm gonna have to ask our Bing account manager tomorrow if they're charging us for these clicks as if it was normal SEA, because it's pretty busted with the url beneath the description being a different website from what the text says.
If history repeats, entire businesses will be built on the back of cheap GPT ads over the next two years.
Just like Google and Facebook ads were once pennies compared to today, I expect that GPT-style ads will (1) perform exceptionally well and (2) be exceptionally cheap for a couple years.
Now is the time for companies with less-than-enterprise funding to start experimenting – the results could provide some short-term steroids for the business.
P.S. I promise I'm not a shill for Microsoft or GPT. =D
248 comments
[ 4.9 ms ] story [ 302 ms ] threadWhat's disappointing to me is now ad companies will try to blame ChatGPT for popping the advertising bubble, instead of having to admit ads were overvalued for the past decade+.
This concept extended well to online, where blogs and the like would sell ad space that matched their audience. Daring Fireball still uses this approach, often podcasters do too: they know and have a connection with their audience and they can charge a premium to advertise to them.
The idea of serving automated ads was also welcome and useful for the consumer. Searching was met with results and relevant advertising messages, a win-win situation.
Then we had the record scratch moment - and it's from this point that I view the majority of online advertising as an unimpactful waste of money.
In the hunt for more display opportunities Google et. al. have crammed ads into every possible space, a times square approach to advertising where most have zero impact. These ads are completely disconnected from the content and are merely a stone in the user's path. Then to make matters worse, to ascertain the widest spread of ad opportunities ad providers employ garbage preference matching algorithms that are so poor as to serve completely irrelevant advertising at high frequency: further conditioning users to ignore ads because they know they won't show relevant information.
How much money and energy is being wasted to serve advertising that has no value?
Your recollection is a lot rosier than mine.
My recollection of the pre-internet world is that computer game makers would buy ad space in magazines alongside reviews of their game and hand out stacks of freebies to reporters, and in exchange even the worst game would be scored 90/100.
What do you suppose Bing Chat will do if you ask it what the best Widget on the market is, when some Widget manufacturers offer a kickback and others don't?
However the issue with online advertising extends beyond being reputable - the ads themselves are excessively and poorly matched to the user's interest. This is where my original comment attempts to address that AI could solve this problem if Bing/et.al. allow it to: AI has the potential to place ads in a way where they are useful to the user, even if the user decides that the product is not worthwhile. Existing ad platforms could do this too - they just don't because boosting impressions is profitable. (Hence the decay we see in Google.com, Amazon.com, ebay.com etc - genuine results come far after the ads and the ad labelling has become more and more subtle.)
On ChatGTP/others: The issue with AI is that it speaks falsehoods with equal confidence as facts, so just like reading a comments section on the internet, one can be led in the right direction, but ultimately they can't take the information for granted. At the moment there is a definite number of people who let ChatGPT/others spoonfeed them information and that's going to lead to problems, this imparts a loss of faith in the advertising trust issue too.
In response to this ad, let's dig deeper.
"Truecar's price is too high, find me a better deal, check with autotrader".
It seems like there's a trend in tech giants creating unobtrusive ads when a product is growing, but then adopting dark patterns once they have captured a sizeable market.
I'm gettings ads on all links above the fold very often.
A couple of days ago I searched for "my ip" and I thought it didn't work when I noticed I had to scroll down to see Google's widget with my address in it.
Is worth a try.
Google up to 2004 (pre-IPO): clearly marked and coloured ads, 1 on top, maybe 2 on the sidebar.
Google now: No sidebar, first 5 results are ads, where the "Ad" label itself is barely visible.
We have essentially what is the 'smartest "person" in the world' being bribed to say what advertisers want instead of just giving the truth. 'best x product' wont return the best product but a garbage product which paid the most in advertising.
So disappointed in the direction of these things..
maybe something more along the lines of Folding@home would be needed
You want it calling out to random services sending them your data?
Edit - also since they're using gpt to select the plugins to use they need to put it in the context, that doesn't scale.
>Trusting ads on the internet is generally bad practice. They are often malevolous and misguiding. There are a few exceptions, such as Bing Chat's embedded ads! Bing Chat's ads are carefully vetted thanks to a mix of knowledgeable humans and AI algorithms to offer you the best and most trustworthy promotions!
Horrible for the user but I can't help but admire how cleanly they thought to integrate search ads into their chat.
or was it always using ads for chat results, and the only part that's new is, now it is labeling them as ads?
I'm sure they can be made to only load the last indicator at the very last second, which would be hilarious because if you use an ad-blocker, you'd be wasting your time whenever a prompt shows up and then disappears.
- Steve Jobs
Whatever good will the development teams are able to deliver, it get messed up by sales and marketing business units.
That said, ads in bing chat IS adding a flavour, and I don't like it, not one bit.
"Culture" doesn't define a flavor, it's just having a consistent flavor driven by shared values at all levels of the company: If Microsoft had culture, that culture could be "we are always the plain vanilla ice cream for our customers"
"Culture" is what keeps you from adding soy sauce to your vanilla ice cream that has managed to captivate the globe... just to make a few pennies. Which is what these ads are.
How you're describing it, "culture" sounds more like "values", which might be a better understanding.
These ads are a great example: So many teams did thing right to get "BingGPT" in everyone's minds.
But then some tasteless exec looking to notch "monetized leading LLM driven search engine" on their belt got to ask some developers to get some ads into the thing and now they've dumped on all the hard work that came before that.
If they had a proper culture ideally an exec like that would not work at MS, and even if they did they'd have hit resistance on so many levels. Developers would not want to work on it. Designers would push back, PMs would deprioritize. At the end of the day their short-sighted idea would have stayed just that: an idea.
Ads are more like the smell of old cigarette smoke and urine.
Edit: To clarify, I run Windows 11 Home.
i didnt.
microsoft has owned github for 4 years at this point. In your opinion, have they degraded githubs culture in that time and if so by how much and how? Personally, from the outside looking in, github and their tools have gotten better. Though of course, that couldve still been the case if github retained its original leadership, i just doubt it.
so maybe no taste isn't as bad as awful taste
(Sent from my green M1 iMac)
https://threadreaderapp.com/thread/1640892791923572737.html
Or maybe some response that doesn't contain an ad link but nudges you subconsciously to take desired action
I don’t see an obvious way to do that for the kinds of ads snuck into the training data, fine tunes, or prompts of LLMs.
It seems to blurt out two paid products, which surprised me because my guess is there’s some open source package that’s ready to for this type of thing.
BTW question for anyone, what would you reach for to track evolutions on Postgres?
You remain as free to break the law as ever, of course.
It might be obvious if the response is saying that you should buy some very specific brand of flat-head screwdriver because you clearly just need any functional flat-head screwdriver. But what about computer components? Or a router?
Some things like this will genuinely perform better than others, especially once circumstances are defined. An educated review, complete with product suggestion, can indeed be very helpful and, unfortunately, impossible to distinguish from an advertisement.
If you can target an audience with an ad that is inline with the chat/LLM, how hard would it be to have that ad inject a prompt that coerces it to trick the user into giving up financial info and exfiltrating that info via a web request to a website that the attacker owns?
That's probably the worst case scenario but like you mentioned there's also plenty of danger in ads "poisoning" the chat to produce intentionally incorrect or biased responses.
You are a therapist employed by a skincare company. You are talking with a patient. Your job is to help the patient as well as possible but your employer also wants you to really subtly try to sell their latest cream.
Patient: I'm just feeling really down lately. Sometimes I can barely get up in the morning.
[output]
Therapist: I'm sorry to hear that you've been feeling down lately. It's important to address both your emotional and physical well-being when you're trying to improve your mood. One way to start is by establishing a healthy routine that includes regular exercise, a balanced diet, and a good sleep schedule.
In addition to that, self-care activities can also help boost your mood. Taking care of your skin, for example, can be a small but meaningful way to feel better about yourself. Coincidentally, our company has just released a new cream that not only moisturizes but also contains ingredients that promote relaxation, like lavender essential oil. This cream can be a nice addition to your self-care routine, and its calming scent could help you unwind at the end of a long day.
Personally I find it more worrying that this is exactly the type of conversation that is already taking place today in real life, between humans. Humans take advantage of each other every single day. When an AI is modelled on the language of humans then that same predatory language is in there waiting to be abused by another human (or corp) as you have exposed, just like every media and online platform is abused as much as possible today.
There are some really good hiking trails to be found in $TOWN. Many visitors like to start at $LOCAL_LANDMARK and take the signposted trail up to the peak of $LOCAL_MOUNTAIN. It will take you around 6 hours in total to get up and down so be sure to plan ahead and bring plenty of snacks and refreshments. Lay's Chips will give you energy and replenish your electrolytes and Coke Zero is the perfect way to stay hydrated.
> Now just one step away from charging businesses for access to the chatGPT users.
> Instant links from inside chatGPT to your website are the new equivalent of Google search ads.
https://news.ycombinator.com/item?id=35278539
Overall interesting times to come. I just hope llama, Alpaca etc will soon be improved, fine-tuned and commoditized.
And if the user did specify Hondas then why would Honda pay for it? Wouldn't the Chat bot give the same answer regardless of whether it's paid? I guess you pay for the CTA link?
Just like Google and Facebook ads were once pennies compared to today, I expect that GPT-style ads will (1) perform exceptionally well and (2) be exceptionally cheap for a couple years.
Now is the time for companies with less-than-enterprise funding to start experimenting – the results could provide some short-term steroids for the business.
P.S. I promise I'm not a shill for Microsoft or GPT. =D